LangGraph ReAct Agent with MCP

What is LangGraph ReAct Agent with MCP?

This template is a ReAct agent implemented using LangGraph and the Model Context Protocol (MCP). It runs as a Python application and connects to one or more MCP servers to provide tools and capabilities through a unified gateway. It is designed for developers building tool‑using agents.

How to use LangGraph ReAct Agent with MCP?

Install the agent and gateway packages (pip install -e .), then configure MCP servers in gateway/config.json. Start the gateway server (python -m mcp_gateway.server on port 8808), set the gateway URL in langgraph.json, and open the agent in LangGraph Studio or a LangGraph server. The agent will automatically discover tools from the configured MCP servers.

Key features of LangGraph ReAct Agent with MCP

• Implements a ReAct agent with LangGraph and MCP.
• Unified MCP gateway manages multiple MCP server processes.
• Provides tools from filesystem and memory MCP servers.
• Automatic tool discovery from connected MCP servers.
• Easy to extend by adding new MCP servers.
• Open source (MIT License).

Use cases of LangGraph ReAct Agent with MCP

• Reading, writing, and searching files on the local filesystem.
• Creating and querying a knowledge graph (entities and relations).
• Combining filesystem and memory tools in a single agent conversation.
• Building an agent that can use any tool from the MCP ecosystem.

FAQ from LangGraph ReAct Agent with MCP

What is the ReAct agent pattern used here?

The template follows the ReAct (Reasoning + Acting) pattern described in the paper “ReAct: Synergizing Reasoning and Acting in Language Models”. The agent reasons about a task, calls tools from MCP servers, and continues until the task is complete.

What is the Model Context Protocol (MCP)?

MCP is a protocol that allows agents to discover and use tools provided by external servers. The agent connects to an MCP gateway that manages multiple MCP server processes and exposes their tools via a simple HTTP interface.

How do I add more MCP servers?

Edit the gateway/config.json file to add the server’s command and arguments under mcp.servers. The official MCP servers repository (linked in the README) provides ready‑to‑use servers. After restarting the gateway, the agent will automatically discover the new tools.

What license is this template under?

The template is licensed under the MIT License. See the LICENSE file for details.

Does this require a specific LLM or platform?

The template is built with LangGraph and runs in LangGraph Studio or any LangGraph server. It does not mandate a specific model; the LLM is configured through the LangGraph environment (e.g., via .env). The MCP servers themselves are model‑agnostic.